IP Library › Granted Patent US 12670245
Granted Patent B2
US 12670245 · App. 18/999,682 · Granted Jun 30, 2026

Utilizing machine-learning models to determine take-over scores and intelligently secure digital account features

Inventors: Brian Mullins (San Francisco, CA); Jiby Babu (Austin, TX); Nik Shevyrev (San Mateo, CA); Parin Shah (Burnaby, CA)
Assignee: Chime Financial, Inc.
G06F21/54G06F21/316G06F21/51G06F21/6245
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12670245
App. No.
18/999,682
Granted
Jun 30, 2026
Kind
B2
Abstract

The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine-learning models to determine take-over scores and intelligently provide or limit access to account features. In particular, in one or more embodiments, the disclosed systems can train and utilize digital security machine-learning models to generate a take-over score indicating a likelihood that the request to access the secure digital account is unauthorized activity. Based on the determining that the take-over score satisfies a take-over threshold, the disclosed systems can allow access to the secure digital account by providing secure account information but prohibit access to a subset of account features.

Claims (83)

1 . A computer-implemented method comprising:

receiving, via a client device, a request to access a secure digital account;

determining one or more extracted features associated with the client device;

generating, utilizing a digital security machine-learning model, a take-over score based on the one or more extracted features;

upon determining that the take-over score satisfies a take-over threshold, allowing access to the secure digital account by providing, for display via the client device, a first selectable option for a first feature, and a second selectable option for a second feature;

in response to receiving, from the client device, a first selection of the first selectable option, executing the first feature based on the take-over score and based on the first feature being a first type;

in response to receiving, from the client device, a second selection of the second selectable option, prohibiting execution of the second feature based on the take-over score and the second feature being a second type; and

providing, on the client device, a notification that the second feature is unavailable.

2 . The computer-implemented method of claim 1 , wherein determining the one or more extracted features associated with the client device comprises:

identifying an IP address associated with the client device; and

determining a time zone associated with a location corresponding to the IP address.

3 . The computer-implemented method of claim 1 , wherein determining the one or more extracted features associated with the client device comprises:

determining a number of secure accounts the client device attempted to access; or

determining a number of failed logins from an IP address associated with the client device.

4 . The computer-implemented method of claim 1 , wherein:

the first feature is a balance inquiry feature, and executing the first feature based on the take-over score comprises providing an account balance for display on the client device; and

the second feature is a transfer feature, and prohibiting executing of the second feature based on the take-over score comprises prohibiting the client device from accessing the transfer feature.

5 . The computer-implemented method of claim 1 , further comprising:

identifying a first threshold based on the first feature being the first type, and wherein executing the first feature based on the take-over score comprises comparing the take-over score to the first threshold; and

identifying a second threshold based on the second feature being the second type, and wherein prohibiting executing of the second feature based on the take-over score comprises comparing the take-over score to the second threshold.

6 . The computer-implemented method of claim 1 , further comprising:

determining one or more historical client device features associated with the secure digital account;

determining one or more device comparison features by comparing the one or more historical client device features with the one or more extracted features associated with the client device; and

wherein the take-over score is based at least in part on the one or more device comparison features.

7 . The computer-implemented method of claim 6 , wherein:

at least one historical client device feature comprises a historical IP address associated with the secure digital account:

at least one extracted feature associated with the client device comprises a current IP address associated with the client device; and

at least one device comparison feature comprises a distance between a first location associated with the historical IP address and a second location associated with the current IP address.

8 . A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computer system to:

receive, from a client device, a request to access a secure digital account;

determine one or more extracted features associated with the client device;

generate, utilizing a digital security machine-learning model, a take-over score based on the one or more extracted features;

upon determining that the take-over score satisfies a take-over threshold, allowing access to the secure digital account by providing, for display via the client device, a first selectable option for a first feature, and a second selectable option for a second feature;

in response to receiving, from the client device, a first selection of the first selectable option, execute the first feature based on the take-over score and based on the first feature being a first type;

in response to receiving, from the client device, a second selection of the second selectable option, prohibit execution of the second feature based on the take-over score and the second feature being a second type; and

provide, on the client device, a notification that the second feature is unavailable.

9 . The non-transitory computer-readable medium of claim 8 , wherein determining the one or more extracted features associated with the client device comprises:

identifying an IP address associated with the client device; and

determining a time zone associated with a location corresponding to the IP address.

10 . The non-transitory computer-readable medium of claim 8 , wherein determining the one or more extracted features associated with the client device comprises:

determining a number of secure accounts the client device attempted to access; or

determining a number of failed logins from an IP address associated with the client device.

11 . The non-transitory computer-readable medium of claim 8 , wherein:

the first feature is a balance inquiry feature, and executing the first feature based on the take-over score comprises providing an account balance for display on the client device; and

the second feature is a transfer feature, and prohibiting executing of the second feature based on the take-over score comprises prohibiting the client device from accessing the transfer feature.

12 . The non-transitory computer-readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:

identify a first threshold based on the first feature being the first type, and wherein executing the first feature based on the take-over score comprises comparing the take-over score to the first threshold; and

identify a second threshold based on the second feature being the second type, and wherein prohibiting executing of the second feature based on the take-over score comprises comparing the take-over score to the second threshold.

13 . The non-transitory computer-readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:

determine one or more historical client device features associated with the secure digital account;

determine one or more device comparison features by comparing the one or more historical client device features with the one or more extracted features associated with the client device; and

wherein the take-over score is based at least in part on the one or more device comparison features.

14 . The non-transitory computer-readable medium of claim 13 , wherein:

at least one historical client device feature comprises a historical IP address associated with the secure digital account:

at least one extracted feature associated with the client device comprises a current IP address associated with the client device; and

at least one device comparison feature comprises a distance between a first location associated with the historical IP address and a second location associated with the current IP address.

15 . A system comprising:

at least one processor; and

at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:

receive, from a client device, a request to access a secure digital account;

determine one or more extracted features associated with the client device;

generate, utilizing a digital security machine-learning model, a take-over score based on the one or more extracted features;

upon determining that the take-over score satisfies a take-over threshold, allowing access to the secure digital account by providing, for display via the client device, a first selectable option for a first feature, and a second selectable option for a second feature;

in response to receiving, from the client device, a first selection of the first selectable option, execute the first feature based on the take-over score and based on the first feature being a first type;

in response to receiving, from the client device, a second selection of the second selectable option, prohibit execution of the second feature based on the take-over score and the second feature being a second type; and

provide, on the client device, a notification that the second feature is unavailable.

16 . The system of claim 15 , wherein determining the one or more extracted features associated with the client device comprises:

identifying an IP address associated with the client device; and

determining a time zone associated with a location corresponding to the IP address.

17 . The system of claim 15 , wherein determining the one or more extracted features associated with the client device comprises:

determining a number of secure accounts the client device attempted to access; or

determining a number of failed logins from an IP address associated with the client device.

18 . The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to:

identify a first threshold based on the first feature being the first type, and wherein executing the first feature based on the take-over score comprises comparing the take-over score to the first threshold; and

identify a second threshold based on the second feature being the second type, and wherein prohibiting executing of the second feature based on the take-over score comprises comparing the take-over score to the second threshold.

19 . The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to:

determine one or more historical client device features associated with the secure digital account;

determine one or more device comparison features by comparing the one or more historical client device features with the one or more extracted features associated with the client device; and

wherein the take-over score is based at least in part on the one or more device comparison features.

20 . The system of claim 19 , wherein:

at least one historical client device feature comprises a historical IP address associated with the secure digital account:

at least one extracted feature associated with the client device comprises a current IP address associated with the client device; and

at least one device comparison feature comprises a distance between a first location associated with the historical IP address and a second location associated with the current IP address.